Centre for Net Zero (CNZ) has announced the creation of a new international open data community, OpenSynth, in partnership with Linux Foundation Energy (LF Energy). This open community will democratise synthetic data to accelerate the decarbonisation of global energy systems.

Access to smart meter data is essential to rapid and successful energy transitions. Researchers, modellers and policy-makers need to understand how energy demand profiles are changing, in a system that requires greater real time optimisation of demand and supply on the grid.

Yet current global energy modelling and policymaking is often still based on static and highly aggregated data from the past – when energy flowed in one direction, consumer profiles were relatively predictable, and power generation was highly controllable. The system we are transitioning to is very different; wind and solar generation is variable depending on weather conditions, storage (in the form of batteries and electric vehicles) will play a much more important role, and the increasing digitisation of the sector allows for better real time optimisation of demand and supply, including bi-directional flows of energy.

To realise the potential of these changes in full, access to demand data is key – but it is highly restricted for the most part, as a result of privacy protections. Rather than joining widespread calls to unlock raw smart meter data through existing mechanisms, by challenging current data regulations and smart meter legislation, CNZ believes generating synthetic data is the fastest way to achieve widespread, global access to smart meter datasets.

CNZ is already engaged in work that advances these ambitions; our generative AI model, Faraday, outputs synthetic half-hourly consumption data for specific household archetypes. The model is designed to help grid operators, innovators and researchers understand the impacts of electrification, and optimise the design of the future energy system.

LF Energy is an open source foundation accelerating the energy transition by building communities consisting of stakeholders in the technology and energy industries to collaborate with academia and government to develop open source technology solutions, frameworks, specifications, and standards to accelerate digital transformation in power generation, transmission, distribution.

Together, we’re building a community of like-minded organisations, OpenSynth, to empower both holders of raw smart meter data around the world to be able to generate and share synthetic data, and for community members and energy researchers to generate, improve and share algorithms.

The smart meter data that CNZ will share through OpenSynth won’t just be synthetic, but contain important metadata such as property type, EPC rating and low carbon technology (LCT) ownership, including heat pumps, electric vehicles and batteries. This will enable better understanding of behind-the-meter changes and inform the ongoing development of future demand profiles for different demographics.

OpenSynth was officially launched at an event at Octopus Energy HQ, London, in April. The team outlined its core goals, which include:

(1) To create a one-stop-shop for synthetic energy data, including data, algorithms, best practices, benchmarking, etc

(2) To encourage more people to create and share synthetic data, to build up a vast pool of diverse datasets

(3) To spread the adoption of synthetic data in academia, industry and within government, to accelerate the decarbonisation of energy systems.

The event also included a panel discussion on what comprises ‘good’ synthetic energy data. We were joined by world-leading academics Dr Pascal Van Hentenryck from Georgia Institute of Technology and Dr Phil Grünewald from the University of Oxford, who CNZ is collaborating with on a technical paper that will evaluate synthetic data using the common concepts of quality, utility and privacy.

If you’re interested in receiving updates on OpenSynth, feeding into foundational work and/or becoming a community member, please sign up here.